Borrowing it
Nothing to install: this file belongs to vmehera123/leashd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vmehera123/leashd/main/.claude/skills/release-prep/SKILL.mdgit clone --depth 1 https://github.com/vmehera123/leashdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vmehera123/leashd/release-prep)<a href="https://agentmods.dev/skills/vmehera123/leashd/release-prep"><img src="https://agentmods.dev/badge/skills/vmehera123/leashd/release-prep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vmehera123/leashd/release-prep"><img src="https://agentmods.dev/badge/skills/vmehera123/leashd/release-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.02607 |
| Opus 5.5 | $0.00051 | $0.01043 |
| Sonnet 5.5 | $0.00025 | $0.00521 |
| Haiku 4.5 | $0.00013 | $0.00261 |
Grade A, and why
release-prep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare leashd for release
Get the working tree ready for a release commit: $ARGUMENTS
This skill prepares, it does not ship. Never commit, tag, push or create the GitHub release (publishing a GitHub release triggers .github/workflows/publish.yml, which uploads to PyPI). Finish with a report and a suggested commit message, and let the user do the rest.
Work through the steps in order. Each one depends on the scope found in step 1.
1. Find what is being released
The last release is the newest commit whose subject starts with Release version X.Y.Z. Tags (vX.Y.Z) can lag behind, so trust the commit.
git log --grep='^Release version' -1 --format='%h %s' | cut -c1-60
git log <last-release>..HEAD --oneline
git diff <last-release> --stat # commits + staged + unstaged
git status --short
Everything after that commit is unreleased, including staged and unstaged work. Read the diff of leashd/ (not just the stat) well enough to say, in user terms, what changed: new commands, new config, changed defaults, removed things, bug fixes. This list drives every later step, so do not build it from the existing changelog entries alone. They can be missing things or describe work that was later reverted.
Never git stash here. The user keeps a deliberate staged/unstaged split and stash flattens it.
2. Choose the version
Classify the unreleased changes against the last released version X.Y.Z:
| Bump | When |
|---|---|
Patch X.Y.Z+1 |
Bug fixes only. Nothing a user could newly do, nothing they must change. |
Minor X.Y+1.0 |
Any new user-facing feature (command, flag, config key, connector behaviour, policy capability), with or without fixes. Small breaking changes fit here too: a changed default, a renamed option, a prompt that now asks where it did not. |
Major X+1.0.0 |
A new architecture or large refactor, a removed runtime or subsystem, or breaking changes that force users to redo their setup. |
The highest category present wins. One added entry among ten fixes is a minor release.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 26d ago First seen · 154 lines · 127 tokens per session scan A 8f29d830635d
release-prep is a skill published in the GitHub repository vmehera123/leashd (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 127 tokens to every session and 2,607 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
release-gate-loop
A release check that tests a change, reports whether it passes, and can run a limited fix-and-retest cycle. A release is the act of making a software version available.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
ship
Pre-release gate. Run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
ship-workflow
Resumable shipping lifecycle: reconciles current Git and GitHub facts from any entry (dirty default or feature branch, local commits, published branch, open PR, existing manual or native stack, merged work), commits dirty work as lossless logical commits, publishes or reuses the PR, requires current CI and review…
blueprint-refactor-tranche
Take ONE target from the plan and land it without changing behaviour: guard it on the untouched code, move it verbatim, prove the equivalence by running both, mutation-sweep the tests, pass every gate, open a PR and merge it on green CI — or decline it with the cost written down.